Home / Current Issue / Paper 1708968
Review Paper: AI-Driven Plant Disease Diagnosis ? A Deep Learning Approach in Precision Agriculture
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence, Data Science, Agriculture
Abstract
Plant diseases have historically threatened the bounty of the earth, jeopardizing global food security and farmers? livelihoods. Traditional detection methods ? rooted in manual labor and laboratory analysis ? remain time-consuming, costly, and inadequate for large-scale farming. As the sun of modern technology rises, artificial intelligence (AI) offers a radiant path forward. Deep learning, a branch of AI, has become the harbinger of precision agriculture, automating plant disease diagnosis with speed and uncanny accuracy. Convolutional Neural Networks (CNNs) process intricate images of diseased leaves, learning to detect the faintest signs of infection. Through transfer learning, AI models build upon existing knowledge, adapting to new plant varieties and disease types with nimble precision. Image processing and data augmentation bolster model performance, overcoming the hurdles of varied environments and data scarcity. This marriage of tradition and innovation empowers farmers to make data-driven decisions, safeguarding their harvests and minimizing pesticide use. Despite these advancements, challenges persist: inconsistent environmental conditions, limited high-quality datasets, and computational constraints in resource-poor settings. Real-world deployment demands lightweight models, accessible interfaces, and collaborations across disciplines. As deep learning interweaves with IoT and edge computing, the promise of real-time, farm-ready diagnosis draws closer. In this paper, we illuminate the journey of AI-driven plant disease diagnosis ?its triumphs, its trials, and its boundless potential. This convergence of deep learning and precision agriculture heralds a new dawn for sustainable farming and global food security.
Keywords
Artificial Intelligence, Deep Learning, Precision Agriculture, Convolutional Neural Networks, Image Processing
References
[1] Journal Article (Deep Learning in Plant Disease Detection) Singh, D., Misra, A. K., & Kumar, A. (2024). Deep learning models for plant disease detection: A comprehensive review. Artificial Intelligence Review, 57(2), 1234– 1260. https:// 10944-7
[2] Journal Article (CNNs for Plant Disease Identification) Kumar, V., & Sharma, P. (2023). Application of convolutional neural networks in crop disease identification: Accuracy and deployment. Journal of Intelligent Computing and Research, 12(4), 56 –72. https://
[3] Journal Article (Real-time Disease Detection with CNNs on FPGA) Chen, L., Zhao, X., & Li, Y. (2024). Edge deployment of convolutional neural networks for plant disease detection using PYNQ FPGA platform. Computers and Electronics in Agriculture, 200, 107489. https://
[4] Review Article (AI in Precision Agriculture) Patel, S., & Desai, M. (2024). Artificial intelligence in precision agriculture: Trends and applications. Frontiers in Plant Science, 15, 1356260. https://
[5] Web Article (AI Impact in Indian Agriculture) Wikipedia contributors. (2024, May 15). Artificial intelligence in India. Wikipedia. Retrieved June 1, 2025, from https://en.wikipedia.org/wiki/Artificial_intellige nce_in_India
[6] Web Article (Plantix Mobile App) Wikipedia contributors. (2024, March 10). Plantix. Wikipedia. Retrieved June 1, 2025, from https://en.wikipedia.org/wiki/Plantix
How to cite this paper
@article{1708968,
author = {Mansi Bapu Zanje, Sneha Balu Shirke, Ishwari Sanjay Yadav, Prof. B. B. Deshmukh},
title = {Review Paper: AI-Driven Plant Disease Diagnosis ? A Deep Learning Approach in Precision Agriculture},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {12},
pages = {241-245},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1708968.pdf},
abstract = {Plant diseases have historically threatened the bounty of the earth, jeopardizing global food security and farmers? livelihoods. Traditional detection methods ? rooted in manual labor and laboratory analysis ? remain time-consuming, costly, and inadequate for large-scale farming. As the sun of modern technology rises, artificial intelligence (AI) offers a radiant path forward. Deep learning, a branch of AI, has become the harbinger of precision agriculture, automating plant disease diagnosis with speed and uncanny accuracy. Convolutional Neural Networks (CNNs) process intricate images of diseased leaves, learning to detect the faintest signs of infection. Through transfer learning, AI models build upon existing knowledge, adapting to new plant varieties and disease types with nimble precision. Image processing and data augmentation bolster model performance, overcoming the hurdles of varied environments and data scarcity. This marriage of tradition and innovation empowers farmers to make data-driven decisions, safeguarding their harvests and minimizing pesticide use. Despite these advancements, challenges persist: inconsistent environmental conditions, limited high-quality datasets, and computational constraints in resource-poor settings. Real-world deployment demands lightweight models, accessible interfaces, and collaborations across disciplines. As deep learning interweaves with IoT and edge computing, the promise of real-time, farm-ready diagnosis draws closer. In this paper, we illuminate the journey of AI-driven plant disease diagnosis ?its triumphs, its trials, and its boundless potential. This convergence of deep learning and precision agriculture heralds a new dawn for sustainable farming and global food security.},
keywords = {Artificial Intelligence, Deep Learning, Precision Agriculture, Convolutional Neural Networks, Image Processing},
month = {June},
}